Systems and methods of detecting intent of spatial control
Inventors
Summer, Matthew D. • Bowman, William S. • Falendysz, Andrew D. • Makovy, Kevin M. • Hedman, Daniel R. • Truesdell, Bradley D.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11886182-B2
Publication Date
2024-01-30
Expiration Date
Abstract
Systems and methods of manipulating/controlling robots. In many scenarios, data collected by a sensor (connected to a robot) may not have very high precision (e.g., a regular commercial/inexpensive sensor) or may be subjected to dynamic environmental changes. Thus, the data collected by the sensor may not indicate the parameter captured by the sensor with high accuracy. The present robotic control system is directed at such scenarios. In some embodiments, the disclosed embodiments can be used for computing a sliding velocity limit boundary for a spatial controller. In some embodiments, the disclosed embodiments can be used for teleoperation of a vehicle located in the field of view of a camera.
Core Innovation
The patent describes a rugged, platform-agnostic robotic control system that infers operator intent from low-precision inertial sensing. It provides direction-intent arbitration in which an initial desired velocity vector is axis-snapped to the nearest principal axis within an axis-snapping tolerance value, and it applies regime arbitration by using linear velocity ratios and angular velocity ratios so unintended linear or angular components are ignored.
The system transforms motion representations between a global reference frame and a control reference frame and sends a final desired velocity vector to at least a portion of the vehicle. It computes a misalignment angle representing a deviation between the initial desired velocity vector direction and the nearest principal axis direction and, when the misalignment angle is within tolerance, rotates the initial desired velocity vector so the final desired velocity vector is parallel to the nearest principal axis direction. When outside the tolerance, axis snapping is not applied.
The patent further includes computing a sliding velocity limit boundary for a spatial controller using a first position boundary and updating it to a second position boundary based on a displacement vector. It also describes inertial velocity filtering that includes bias estimation, low-pass filtering, and integration with rotation into an inertial frame, inertial DOF locking using locked degrees of freedom to hold or level behaviors, and multiple teleoperation modes including traverse mode, reorient mode, and manipulate mode using remote camera and position data with reference-frame transformations.
Claims Coverage
The provided claims include three independent inventive methods: (1) detecting an intent of spatial control via principal-axis direction snapping, (2) detecting an intended regime of a velocity command via linear/angular ratio arbitration and ignoring velocity components, and (3) computing a sliding velocity limit boundary for a spatial controller to generate a target velocity. Together, the independent claims cover axis-snapping direction arbitration, regime arbitration by ratio-based ignoring, and sliding boundary computation for target-velocity generation.
Principal-axis velocity intent detection with misalignment-based axis snapping
Receiving spatial motion data representing desired motion of at least a portion of a vehicle, computing an initial desired velocity vector representing desired linear velocity or desired angular velocity, transforming the initial desired velocity vector from a global reference frame into a control reference frame, identifying a nearest principal axis direction from principal axis directions parallel to principal axes of the control reference frame, computing a misalignment angle representing deviation from the nearest principal axis direction, and defining a final desired velocity vector by rotating the initial desired velocity vector such that it is parallel to the nearest principal axis direction when the misalignment angle is less than or equal to an axis-snapping tolerance value; and sending information indicating the final desired velocity vector to at least the portion of the vehicle.
Velocity regime arbitration using linear and angular ratio-based ignoring
Receiving spatial motion data representing desired motion of at least a portion of a vehicle, computing a desired linear velocity vector and a desired angular velocity vector, computing a linear ratio dividing a magnitude of the desired linear velocity vector by a linear magnitude threshold and computing an angular ratio dividing a magnitude of the desired angular velocity vector by an angular magnitude threshold, upon determining that the linear ratio or the angular ratio satisfies one or more rules ignoring the desired linear velocity vector, upon determining that the linear ratio or the angular ratio satisfies one or more rules ignoring the desired angular velocity vector, and sending data indicating the desired linear velocity vector and the desired angular velocity vector to at least the portion of the vehicle.
Sliding velocity limit boundary computation for target velocity generation
Receiving information describing a first position boundary of the spatial controller corresponding to a maximum velocity of the vehicle or a part thereof, receiving information describing a current position of the spatial controller, using the current position to determine that the current position is outside the first position boundary, identifying a displacement vector corresponding to a difference between the current position and the first position boundary, adding the displacement vector to the first position boundary to generate a second position boundary such that the current position is at the second position boundary, updating the first position boundary as the second position boundary, and computing a target velocity based on a difference between the current position and a center of the first position boundary such that the vehicle or the part thereof moves in accordance with the target velocity.
The independent claims concentrate on transforming controller-derived spatial motion into a control reference frame and snapping the velocity direction to a nearest principal axis when within an axis-snapping tolerance, determining whether to ignore desired linear and/or desired angular velocity components using rules based on linear and angular ratios relative to thresholds, and computing a sliding velocity limit boundary by updating position boundaries using a displacement vector, then generating a target velocity from the updated boundary center.
Stated Advantages
Provides direction-intent arbitration by axis-snapping an initial desired velocity vector to the nearest principal axis within a tolerance.
Ignores unintended linear or angular components through regime arbitration using linear/angular velocity ratios.
Infers operator intent from low-precision inertial sensing.
Provides sliding velocity limit boundary computation based on a maximum velocity position boundary and updates to maintain a relationship to the current position.
Documented Applications
Teleoperation of vehicles using traverse mode, reorient mode, and manipulate mode, using remote camera and position data with reference-frame transformations.
Interested in licensing this patent?